Zhongjie Duan
|
8332ecebb7
|
Merge pull request #1034 from modelscope/video_as_prompt
Video as prompt
|
2025-11-04 17:32:50 +08:00 |
|
Zhongjie Duan
|
401d7d74a5
|
Merge pull request #1025 from krahets/patch-1
Fix sinusoidal_embedding calculation for bf16 precision.
|
2025-11-04 15:08:11 +08:00 |
|
Yudong Jin
|
b8d7d55568
|
Fix dtype issue in time embedding calculation
|
2025-11-01 03:11:03 +08:00 |
|
Zhongjie Duan
|
a30ed9093f
|
Merge pull request #1018 from modelscope/longcat
support LongCat-Video
|
2025-10-30 13:45:03 +08:00 |
|
Artiprocher
|
b73e713028
|
support LongCat-Video
|
2025-10-30 13:38:14 +08:00 |
|
yjy415
|
e0eabaa426
|
Krea realtime video (#1011)
* krea-realtime-video
* Add Krea real-time video inference and training support
* Delete .gitignore
* update README
* update README
---------
Co-authored-by: Artiprocher <wangye87v5@hotmail.com>
Co-authored-by: Jintao Huang <huangjintao.hjt@alibaba-inc.com>
Co-authored-by: Zhongjie Duan <35051019+Artiprocher@users.noreply.github.com>
|
2025-10-27 19:09:28 +08:00 |
|
Zhongjie Duan
|
538017177a
|
Merge pull request #1006 from lzws/main
add wan2.2-S2V-14B training
|
2025-10-22 09:55:21 +08:00 |
|
lzws
|
30292d9411
|
update wan2.2-S2V training
|
2025-10-21 19:59:44 +08:00 |
|
lzws
|
b168d7aa8b
|
update wans2v training
|
2025-10-21 10:39:30 +08:00 |
|
lzws
|
8ea45b0daa
|
update wans2v training
|
2025-10-21 10:34:48 +08:00 |
|
Zhongjie Duan
|
0a1c172a00
|
Merge pull request #984 from modelscope/animate-bugfix
bugfix
|
2025-10-10 15:42:20 +08:00 |
|
Artiprocher
|
77fac2a03f
|
bugfix
|
2025-10-10 15:41:39 +08:00 |
|
Zhongjie Duan
|
084bc2fc78
|
Merge pull request #969 from modelscope/bugfix953
fix bug in issue 953
|
2025-09-30 13:00:15 +08:00 |
|
Artiprocher
|
c63d474b60
|
fix bug in issue 953
|
2025-09-30 12:59:44 +08:00 |
|
Zhongjie Duan
|
7540568156
|
support wan2.2-animate-14b (#968)
|
2025-09-30 12:57:16 +08:00 |
|
Zhongjie Duan
|
c5d426c254
|
Merge branch 'main' into wan-animate
|
2025-09-30 12:56:28 +08:00 |
|
Artiprocher
|
a36f2f6032
|
support wan2.2-animate-14b
|
2025-09-30 12:45:56 +08:00 |
|
lzws
|
ed256ef8be
|
fix wan vace bug (#960)
* fix wan vace bug
|
2025-09-26 13:49:27 +08:00 |
|
Zhongjie Duan
|
15079a6cb8
|
Merge pull request #944 from baolef/dev
fix: fix the undefined vace typo
|
2025-09-25 15:58:24 +08:00 |
|
Zhongjie Duan
|
c084d6377b
|
Merge pull request #952 from modelscope/bugfix-vace
Update wan_video_new.py
|
2025-09-25 15:34:22 +08:00 |
|
Zhongjie Duan
|
e9bc42f233
|
Update wan_video_new.py
|
2025-09-25 15:34:09 +08:00 |
|
Zhongjie Duan
|
0d6de58af9
|
Merge pull request #949 from modelscope/qwen-image-edit-multi
update qwen-image-edit training script
|
2025-09-25 11:07:38 +08:00 |
|
Artiprocher
|
acbf932974
|
update qwen-image-edit training script
|
2025-09-25 11:07:01 +08:00 |
|
Baole Fang
|
9d64ed7042
|
fix: fix the undefined vace typo
|
2025-09-24 16:55:47 +08:00 |
|
Zhongjie Duan
|
0b4b337e9a
|
Merge pull request #933 from lzws/main
update wan2.2-VACE-Fun-A14B
|
2025-09-24 09:56:37 +08:00 |
|
Zhongjie Duan
|
99908d9a1c
|
Merge pull request #940 from mi804/eligen_poster
support eligen-poster
|
2025-09-23 17:49:37 +08:00 |
|
mi804
|
73ced7a46d
|
support eligen-poster
|
2025-09-23 17:41:48 +08:00 |
|
Zhongjie Duan
|
32b8b9b51e
|
Merge pull request #910 from ldiex/main
Fix gradient checkpointing in WAN VACE blocks
|
2025-09-23 12:23:12 +08:00 |
|
Zhongjie Duan
|
f6534a5b63
|
Merge pull request #909 from huarzone/fix_bug
fix load gif
|
2025-09-23 12:22:00 +08:00 |
|
Zhongjie Duan
|
034c9b6c60
|
Qwen-Image-Edit-2509 (#937)
* qwen-image-edit-2509
|
2025-09-22 20:37:11 +08:00 |
|
lzws
|
76335e0fe5
|
uodate wan2.2-VACE-Fun
|
2025-09-22 02:14:20 +08:00 |
|
lzws
|
c0b589d934
|
add wan2.2-VACE-Fun infereance and trining
|
2025-09-22 01:57:05 +08:00 |
|
Zhongjie Duan
|
833ba1e1fa
|
update vram management strategy (#929)
|
2025-09-18 16:53:13 +08:00 |
|
Artiprocher
|
7a5974d964
|
update vram management strategy
|
2025-09-18 16:51:53 +08:00 |
|
Zhongjie Duan
|
b0abdaffb4
|
Qwen image split training Bug Fix (#926)
* bugfix
|
2025-09-17 20:53:46 +08:00 |
|
Zhongjie Duan
|
e9f29bc402
|
Merge pull request #921 from modelscope/qwen-image-distill-dmd2-lora
support qwen-image-distill-dmd2-lora
|
2025-09-16 19:43:59 +08:00 |
|
Artiprocher
|
1a7f482fbd
|
support qwen-image-distill-dmd2-lora
|
2025-09-16 19:43:07 +08:00 |
|
Tianlin Pan
|
3a0d51d100
|
Fix gradient checkpointing in WAN VACE blocks
|
2025-09-14 16:21:46 +08:00 |
|
Kared
|
bffdb901ed
|
fix load gif
|
2025-09-13 21:01:44 +08:00 |
|
Zhongjie Duan
|
d93e8738cd
|
Merge pull request #902 from xycdx/feature/improve-fastblend
add torch implementation for interpolation
|
2025-09-11 11:45:55 +08:00 |
|
xycdx
|
7e5ce5d5c9
|
Update diffsynth/extensions/FastBlend/patch_match.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-09-10 20:48:54 +08:00 |
|
xycdx
|
7aef554d83
|
add torch implementation for interpolation
- Implement bilinear interpolation kernel using Numba
- Benchmark shows 2x speedup compared to CPU version
- Closes #817
|
2025-09-10 20:39:35 +08:00 |
|
Zhongjie Duan
|
090074e395
|
Merge pull request #899 from modelscope/version_update_1.1.8
Update setup.py
v1.1.8
|
2025-09-09 18:43:03 +08:00 |
|
Zhongjie Duan
|
2dcdeefca8
|
Update setup.py
|
2025-09-09 18:42:39 +08:00 |
|
Zhongjie Duan
|
452a6ca5cf
|
Merge pull request #898 from modelscope/direct_distill
support direct distill
|
2025-09-09 16:16:32 +08:00 |
|
Artiprocher
|
d6cf20ef33
|
support direct distill
|
2025-09-09 16:12:31 +08:00 |
|
Zhongjie Duan
|
efdd6a59b6
|
Merge pull request #892 from modelscope/dev2-dzj
refine training framework
|
2025-09-04 15:53:52 +08:00 |
|
Artiprocher
|
42ec7b08eb
|
bugfix
|
2025-09-04 15:45:39 +08:00 |
|
Artiprocher
|
d049fb6d1d
|
bugfix
|
2025-09-04 15:44:37 +08:00 |
|
Artiprocher
|
144365b07d
|
merge data process to training script
|
2025-09-04 15:18:56 +08:00 |
|